Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13348
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly related to vectors and string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ennifer
    -0.53
    出版年
    -0.53
    つ
    -0.50
    мут
    -0.50
    ToListAsync
    -0.50
     bohat
    -0.49
    publique
    -0.48
    şekkür
    -0.48
     innehå
    -0.48
    iligt
    -0.47
    POSITIVE LOGITS
    ChildScrollView
    0.85
    UserScript
    0.80
     AssemblyTitle
    0.79
    CopyWith
    0.74
    tableFuture
    0.73
    URLException
    0.72
    reactstrap
    0.66
    ruptedException
    0.63
    endphp
    0.62
    Przypisy
    0.62
    Activations Density 0.164%

    No Known Activations